The evaluation metric is
Mean Average Precision at 20 (MAP@20)
on the test set. A good explanation of the metric can be found
[here](http://fastml.com/what-you-wanted-to-know-about-mean-average-precision/)
.
In our case, there is only one true corresponding image. So for a description, suppose your algorithm find the corresponding image in top 20 of your returned list and its ranked i-th, MAP@20 gives a score of
$$score = \frac{20+1-i}{20}$$
For example, if its ranked 1st, you get 1; if its 11th, you get 0.5; if its 20th, you get 0.05. If the corresponding image is not in your top 20 list, you get 0 score. The overall score is calculated as the average score on the test set.
We divide the test set into two splits: public split and private split. Results on the Leaderboard are evaluated on public split and the private split is used for grading.